Model logo

Qwen3 30B A3B Thinking 2507

Instruct
Reasoning
Tools
Qwen3-30B-A3B-Thinking-2507, released in July 2025 as part of the Qwen3 series, is an advanced Mixture-of-Experts large language model optimized for high-level reasoning. Building on the 30B A3B architecture, it introduces significant improvements in logical reasoning, mathematics, science, and coding performance, while excelling on academic benchmarks that require expert-level problem-solving. The model also enhances instruction following, tool usage, and long-context comprehension with support for up to 256,000 tokens, making it particularly effective for complex multi-step workflows and research applications.
Provider
Context Size
Throughput
Latency
Input Cost
Output Cost

Usage

Generate your API key and query the model through the OpenAI-compatible interface. The preference parameter allows you to define the routing strategy. For more details, see the documentation.

>Enter ↵